Added AssignTaxonomy step

public/biopet-extensions/src/main/scala/nl/lumc/sasc/biopet/extensions/qiime/AssignTaxonomy.scala

+package nl.lumc.sasc.biopet.extensions.qiime
+
+import java.io.File
+
+import nl.lumc.sasc.biopet.core.{ Version, BiopetCommandLineFunction }
+import nl.lumc.sasc.biopet.utils.config.Configurable
+import org.broadinstitute.gatk.utils.commandline.Input
+
+/**
+ * Created by pjvan_thof on 12/4/15.
+ */
+class AssignTaxonomy(val root: Configurable) extends BiopetCommandLineFunction with Version {
+  executable = config("exe", default = "assign_taxonomy.py")
+
+  @Input(required = true)
+  var inputFasta: File = _
+
+  @Input(required = false)
+  var read_1_seqs_fp: Option[File] = None
+
+  @Input(required = false)
+  var read_2_seqs_fp: Option[File] = None
+
+  @Input(required = false)
+  var id_to_taxonomy_fp: Option[File] = config("id_to_taxonomy_fp")
+
+  @Input(required = false)
+  var reference_seqs_fp: Option[File] = config("reference_seqs_fp")
+
+  @Input(required = false)
+  var training_data_properties_fp: Option[File] = config("training_data_properties_fp")
+
+  var single_ok: Boolean = config("single_ok", default = false)
+  var no_single_ok_generic: Boolean = config("no_single_ok_generic", default = false)
+
+  var amplicon_id_regex: Option[String] = config("amplicon_id_regex")
+  var header_id_regex: Option[String] = config("header_id_regex")
+  var assignment_method: Option[String] = config("assignment_method")
+  var sortmerna_db: Option[String] = config("sortmerna_db")
+  var sortmerna_e_value: Option[String] = config("sortmerna_e_value")
+  var sortmerna_coverage: Option[String] = config("sortmerna_coverage")
+  var sortmerna_best_N_alignments: Option[String] = config("sortmerna_best_N_alignments")
+  var sortmerna_threads: Option[String] = config("sortmerna_threads")
+  var blast_db: Option[String] = config("blast_db")
+  var confidence: Option[String] = config("confidence")
+  var min_consensus_fraction: Option[String] = config("min_consensus_fraction")
+  var similarity: Option[String] = config("similarity")
+  var uclust_max_accepts: Option[String] = config("uclust_max_accepts")
+  var rdp_max_memory: Option[String] = config("rdp_max_memory")
+  var blast_e_value: Option[String] = config("blast_e_value")
+  var outputDir: File = _
+
+  def versionCommand = executable + " --version"
+  def versionRegex = """Version: (.*)""".r
+
+  override def beforeGraph(): Unit = {
+    super.beforeGraph()
+    require(outputDir != null)
+  }
+
+  def cmdLine = executable +
+    required("-o", inputFasta) +
+    optional("--read_1_seqs_fp", read_1_seqs_fp) +
+    optional("--read_2_seqs_fp", read_2_seqs_fp) +
+    optional("-t", id_to_taxonomy_fp) +
+    optional("-r", reference_seqs_fp) +
+    optional("-p", training_data_properties_fp) +
+    optional("--amplicon_id_regex", amplicon_id_regex) +
+    optional("--header_id_regex", header_id_regex) +
+    optional("--assignment_method", assignment_method) +
+    optional("--sortmerna_db", sortmerna_db) +
+    optional("--sortmerna_e_value", sortmerna_e_value) +
+    optional("--sortmerna_coverage", sortmerna_coverage) +
+    optional("--sortmerna_best_N_alignments", sortmerna_best_N_alignments) +
+    optional("--sortmerna_threads", sortmerna_threads) +
+    optional("--blast_db", blast_db) +
+    optional("--confidence", confidence) +
+    optional("--min_consensus_fraction", min_consensus_fraction) +
+    optional("--similarity", similarity) +
+    optional("--uclust_max_accepts", uclust_max_accepts) +
+    optional("--rdp_max_memory", rdp_max_memory) +
+    optional("--blast_e_value", blast_e_value) +
+    required("--output_dir", outputDir)
+
+}

public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsQiimeRatx.scala → public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsQiimeRtax.scala

 package nl.lumc.sasc.biopet.pipelines.gears
 
 import nl.lumc.sasc.biopet.core.BiopetQScript
-import nl.lumc.sasc.biopet.extensions.qiime.{ PickRepSet, PickOtus }
+import nl.lumc.sasc.biopet.extensions.qiime.{AssignTaxonomy, PickRepSet, PickOtus}
 import nl.lumc.sasc.biopet.utils.config.Configurable
 import org.broadinstitute.gatk.queue.QScript
 
 /**
  * Created by pjvan_thof on 12/4/15.
  */
-class GearsQiimeRatx(val root: Configurable) extends QScript with BiopetQScript {
+class GearsQiimeRtax(val root: Configurable) extends QScript with BiopetQScript {
 
   var fastaR1: File = _
 
-  var fastqR2: Option[File] = None
+  var fastaR2: Option[File] = None
+
+  override def fixedValues = Map("assigntaxonomy" -> Map("assignment_method" -> "rtax"))
 
   def init() = {
     require(fastaR1 != null)
@@ -31,5 +33,13 @@ class GearsQiimeRatx(val root: Configurable) extends QScript with BiopetQScript
     pickRepSet.logFile = Some(new File(pickRepSet.outputDir, fastaR1.getName
       .stripSuffix(".fasta").stripSuffix(".fa").stripSuffix(".fna") + ".log"))
     add(pickRepSet)
+
+    val assignTaxonomy = new AssignTaxonomy(this)
+    assignTaxonomy.outputDir = new File(outputDir, "assign_taxonomy")
+    assignTaxonomy.jobOutputFile = new File(assignTaxonomy.outputDir, ".assign_taxonomy.out")
+    assignTaxonomy.inputFasta = pickRepSet.outputFasta.get
+    assignTaxonomy.read_1_seqs_fp = Some(fastaR1)
+    assignTaxonomy.read_2_seqs_fp = fastaR2
+    add(assignTaxonomy)
   }
 }

public/gears/src/main/scala/nl/lumc/sasc/biopet/pipelines/gears/GearsSingle.scala

@@ -109,10 +109,10 @@ class GearsSingle(val root: Configurable) extends QScript with SummaryQScript wi
     }
 
     if (gearsUserQiimeRtax) {
-      val qiimeRatx = new GearsQiimeRatx(this)
+      val qiimeRatx = new GearsQiimeRtax(this)
       qiimeRatx.outputDir = new File(outputDir, "qiime_ratx")
       qiimeRatx.fastaR1 = fastaR1
-      qiimeRatx.fastqR2 = fastaR2
+      qiimeRatx.fastaR2 = fastaR2
       qiimeRatx.init()
       qiimeRatx.biopetScript()
       addAll(qiimeRatx.functions)